{"id":"W4398331983","doi":"10.7910/dvn/ii5jzg/0wo44w","title":"MSP_F_100_NFL_4_1.xlsx","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Context (archaeology); Resolution (logic); Computer science; History; Artificial intelligence; Archaeology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005578073,0.0003929698,0.0005845954,0.000282981,0.0001873599,0.0006255241,0.005412709,0.0003285763,0.007089812],"category_scores_gemma":[0.001122307,0.0003708038,0.0003119242,0.0009986719,0.0001374634,0.0006647031,0.003236295,0.0009356042,0.4957119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001101526,"about_ca_system_score_gemma":0.0004330299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003654405,"about_ca_topic_score_gemma":0.00005246574,"domain_scores_codex":[0.996323,0.000266715,0.0004568616,0.001233722,0.001146293,0.0005733485],"domain_scores_gemma":[0.9952106,0.0003332316,0.0001770812,0.003679898,0.0001512403,0.0004478806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007273148,0.00007679552,0.000004268074,0.000131849,0.00009596378,0.0002732401,0.00001471413,0.000008210091,0.000003841435,0.0001626381,0.9972343,0.00198685],"study_design_scores_gemma":[0.0002060652,0.00005752129,0.00001124708,0.000039315,0.00005155242,0.00001213662,0.000006685111,0.001207592,0.00001835978,0.0001749556,0.9978231,0.0003914468],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[5.720255e-7,0.0000024374,0.01443876,0.0001100277,0.0004204783,0.0002035869,0.9845029,0.0002249594,0.00009631291],"genre_scores_gemma":[0.000003049193,0.0006123042,0.003644231,0.001087014,0.0003088582,0.00002660425,0.9941266,0.00001431675,0.0001770042],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.4886221,"threshold_uncertainty_score":0.9999685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02254317685125836,"score_gpt":0.2681597623408774,"score_spread":0.245616585489619,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}